[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"model-mistral-7b-instruct-v0-3":3},{"id":4,"slug":5,"name":6,"hf_id":6,"organization":7,"architecture":8,"architecture_config":9,"parameters":14,"parameters_label":15,"context_length":16,"license":17,"downloads":18,"likes":19,"status":20,"description":21,"huggingface_url":22,"created_at":23,"seo":24,"category":26,"family":29,"score":31,"variants":32,"quantizations":33,"requirements":59,"gpu_recommendations":139,"fitting_gpus":203,"community":234},20,"mistral-7b-instruct-v0-3","mistralai\u002FMistral-7B-Instruct-v0.3","mistralai","mistral",{"layers":10,"head_dim":11,"kv_heads":12,"hidden_size":13},32,128,8,4096,6576668672,"6.6B",32768,null,4106867,2812,"published","Classic 7B Mistral, lightweight and fast.","https:\u002F\u002Fhuggingface.co\u002Fmistralai\u002FMistral-7B-Instruct-v0.3","2026-08-12T02:22:24+00:00",{"title":6,"description":21,"image":17,"robots":25,"canonical_url":17},"index, follow",{"name":27,"slug":28},"LLM","llm",{"name":30,"slug":8},"Mistral",0.0564,[],[34,39,44,48,52,56],{"format":35,"bits":36,"size_factor":37,"quality_loss":38},"AWQ",4,0.263,0.03,{"format":40,"bits":41,"size_factor":42,"quality_loss":43},"FP16",16,1,0,{"format":45,"bits":12,"size_factor":46,"quality_loss":47},"FP8",0.5,0.01,{"format":49,"bits":36,"size_factor":50,"quality_loss":51},"GGUF",0.25,0.05,{"format":53,"bits":36,"size_factor":54,"quality_loss":55},"GPTQ",0.275,0.04,{"format":57,"bits":12,"size_factor":46,"quality_loss":58},"INT8",0.02,{"FP16":60,"FP8":83,"INT8":96,"AWQ":100,"GPTQ":113,"GGUF":126},{"minimum":61,"production":69,"recommended":76},{"scenario":62,"context_length":13,"batch_size":42,"weight_gb":63,"kv_cache_gb":46,"vram_gb":64,"ram_gb":65,"disk_gb":66,"requirement_source":67,"confidence":68},"minimum",13.6,22.15,33.23,60.21,"estimated",0.95,{"scenario":70,"context_length":71,"batch_size":36,"weight_gb":63,"kv_cache_gb":72,"vram_gb":73,"ram_gb":74,"disk_gb":75,"requirement_source":67,"confidence":68},"production",16384,64,136.36,204.55,125.21,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":63,"kv_cache_gb":12,"vram_gb":80,"ram_gb":81,"disk_gb":82,"requirement_source":67,"confidence":68},"recommended",8192,2,38.68,58.02,86.21,{"minimum":84,"production":88,"recommended":92},{"scenario":62,"context_length":13,"batch_size":42,"weight_gb":85,"kv_cache_gb":46,"vram_gb":86,"ram_gb":10,"disk_gb":87,"requirement_source":67,"confidence":68},6.8,13.55,49.61,{"scenario":70,"context_length":71,"batch_size":36,"weight_gb":85,"kv_cache_gb":72,"vram_gb":89,"ram_gb":90,"disk_gb":91,"requirement_source":67,"confidence":68},126.98,190.47,114.61,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":85,"kv_cache_gb":12,"vram_gb":93,"ram_gb":94,"disk_gb":95,"requirement_source":67,"confidence":68},29.69,44.54,75.61,{"minimum":97,"production":98,"recommended":99},{"scenario":62,"context_length":13,"batch_size":42,"weight_gb":85,"kv_cache_gb":46,"vram_gb":86,"ram_gb":10,"disk_gb":87,"requirement_source":67,"confidence":68},{"scenario":70,"context_length":71,"batch_size":36,"weight_gb":85,"kv_cache_gb":72,"vram_gb":89,"ram_gb":90,"disk_gb":91,"requirement_source":67,"confidence":68},{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":85,"kv_cache_gb":12,"vram_gb":93,"ram_gb":94,"disk_gb":95,"requirement_source":67,"confidence":68},{"minimum":101,"production":105,"recommended":109},{"scenario":62,"context_length":13,"batch_size":42,"weight_gb":102,"kv_cache_gb":46,"vram_gb":103,"ram_gb":10,"disk_gb":104,"requirement_source":67,"confidence":68},3.53,9.41,44.5,{"scenario":70,"context_length":71,"batch_size":36,"weight_gb":102,"kv_cache_gb":72,"vram_gb":106,"ram_gb":107,"disk_gb":108,"requirement_source":67,"confidence":68},122.47,183.7,109.5,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":102,"kv_cache_gb":12,"vram_gb":110,"ram_gb":111,"disk_gb":112,"requirement_source":67,"confidence":68},25.36,38.05,70.5,{"minimum":114,"production":118,"recommended":122},{"scenario":62,"context_length":13,"batch_size":42,"weight_gb":115,"kv_cache_gb":46,"vram_gb":116,"ram_gb":10,"disk_gb":117,"requirement_source":67,"confidence":68},3.57,9.47,44.57,{"scenario":70,"context_length":71,"batch_size":36,"weight_gb":115,"kv_cache_gb":72,"vram_gb":119,"ram_gb":120,"disk_gb":121,"requirement_source":67,"confidence":68},122.53,183.79,109.57,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":115,"kv_cache_gb":12,"vram_gb":123,"ram_gb":124,"disk_gb":125,"requirement_source":67,"confidence":68},25.42,38.13,70.57,{"minimum":127,"production":131,"recommended":135},{"scenario":62,"context_length":13,"batch_size":42,"weight_gb":128,"kv_cache_gb":46,"vram_gb":129,"ram_gb":10,"disk_gb":130,"requirement_source":67,"confidence":68},3.65,9.57,44.7,{"scenario":70,"context_length":71,"batch_size":36,"weight_gb":128,"kv_cache_gb":72,"vram_gb":132,"ram_gb":133,"disk_gb":134,"requirement_source":67,"confidence":68},122.64,183.96,109.7,{"scenario":77,"context_length":78,"batch_size":79,"weight_gb":128,"kv_cache_gb":12,"vram_gb":136,"ram_gb":137,"disk_gb":138,"requirement_source":67,"confidence":68},25.53,38.3,70.7,{"recommended":140,"cheapest":158,"performance":168,"min_complexity":185,"cluster_options":199,"no_match":200,"required_vram_gb":110,"candidate_count":201,"usage":202},{"gpu_model":141,"gpu_model_id":79,"gpu_count":42,"total_vram_gb":10,"hour_price":142,"monthly_cost":143,"providers":144,"bandwidth_gbps":147,"fp16_tflops":148,"interconnect_score":149,"parallel_efficiency":42,"score":150,"tier":151,"perf_metric":152,"perf_label":153,"perf_value":154,"workload":17,"cost_metric":155},"RTX 5090",0.3222,235.21,[145,146],"vast","runpod",1792,209,40,0.6866,"cheapest","tok\u002Fs","507.6 tok\u002Fs",507.6,{"effective_value":156,"effective_unit":152,"capacity_factor":157},355.3,0.7,{"gpu_model":159,"gpu_model_id":160,"gpu_count":79,"total_vram_gb":10,"hour_price":161,"monthly_cost":162,"providers":163,"bandwidth_gbps":43,"fp16_tflops":43,"interconnect_score":149,"parallel_efficiency":164,"score":165,"tier":151,"perf_metric":152,"perf_label":166,"perf_value":43,"workload":17,"cost_metric":167},"Tesla V100",17,0.0272,39.71,[145],0.8,0.6353,"0 tok\u002Fs",{"effective_value":43,"effective_unit":152,"capacity_factor":157},{"gpu_model":169,"gpu_model_id":170,"gpu_count":12,"total_vram_gb":171,"hour_price":172,"monthly_cost":173,"providers":174,"bandwidth_gbps":176,"fp16_tflops":177,"interconnect_score":149,"parallel_efficiency":178,"score":179,"tier":180,"perf_metric":152,"perf_label":181,"perf_value":182,"workload":17,"cost_metric":183},"H200 SXM",11,1128,3.5,20440,[175],"lambda",4800,989,0.4,0.2197,"balanced","4351.3 tok\u002Fs",4351.3,{"effective_value":184,"effective_unit":152,"capacity_factor":157},3045.9,{"gpu_model":186,"gpu_model_id":187,"gpu_count":42,"total_vram_gb":188,"hour_price":189,"monthly_cost":190,"providers":191,"bandwidth_gbps":192,"fp16_tflops":193,"interconnect_score":149,"parallel_efficiency":42,"score":194,"tier":151,"perf_metric":152,"perf_label":195,"perf_value":196,"workload":17,"cost_metric":197},"RTX A6000",6,48,0.3001,219.07,[145,175],768,77,0.6318,"217.6 tok\u002Fs",217.6,{"effective_value":198,"effective_unit":152,"capacity_factor":157},152.3,[],false,24,"value",[204,208,212,220,227],{"name":186,"vram_gb":188,"cheapest_hour":189,"cost":205,"provider":145,"estimated_tps":196},{"hourly":189,"daily":206,"monthly":190,"yearly":207},7.2,2628.88,{"name":141,"vram_gb":10,"cheapest_hour":142,"cost":209,"provider":145,"estimated_tps":154},{"hourly":142,"daily":210,"monthly":143,"yearly":211},7.73,2822.47,{"name":213,"vram_gb":188,"cheapest_hour":214,"cost":215,"provider":145,"estimated_tps":219},"L40S",0.4669,{"hourly":214,"daily":216,"monthly":217,"yearly":218},11.21,340.84,4090.04,244.8,{"name":221,"vram_gb":188,"cheapest_hour":222,"cost":223,"provider":145,"estimated_tps":43},"RTX PRO 6000 WS",0.8022,{"hourly":222,"daily":224,"monthly":225,"yearly":226},19.25,585.61,7027.27,{"name":228,"vram_gb":188,"cheapest_hour":229,"cost":230,"provider":145,"estimated_tps":43},"RTX PRO 6000 S",1.0131,{"hourly":229,"daily":231,"monthly":232,"yearly":233},24.31,739.56,8874.76,{"posts_count":43,"benchmarks_count":43}]